Official repository of SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens
-
Updated
Mar 13, 2026 - Jupyter Notebook
Official repository of SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens
Minimum example showing how to setup Singularity with Maniskill3 to run training headless on a cluster.
Very minimal Implementation of Pi-Zero (https://www.pi.website/download/pi0.pdf). Vision Action Flow matching model
Convert ManiSkill HDF5 demonstration trajectories to RLDS / TFDS format for robot learning and VLA data pipelines.
This repository is a modified fork of the official Octo project.It extends the original Octo codebase with tools for adapting Octo to ManiSkill simulation tasks, including ManiSkill-to-RLDS data conversion, Octo fine-tuning scripts, and ManiSkill-based evaluation utilities.
MOPS Data Generation
Add a description, image, and links to the maniskill3 topic page so that developers can more easily learn about it.
To associate your repository with the maniskill3 topic, visit your repo's landing page and select "manage topics."